No article text was recorded for this version.
unitary weight constraint
Version 1 of 143 papers54 conceptsfrozen 2026-10-04
Papers in this version
- Blog: CWY Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel Matrices
- Blog: Gated Orthogonal Recurrent Units: On Learning to Forget
- Blog: DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
- Blog: Recurrent Quantum Neural Networks
- Blog: Neural Controlled Differential Equations with Quantum Hidden Evolutions
- Blog: Unitary Evolution Recurrent Neural Networks
- Blog: Time Adaptive Recurrent Neural Network
- Blog: Full-Capacity Unitary Recurrent Neural Networks
- Blog: Quantum Recurrent Architectures for Text Classification
- Blog: Quantum-inspired Neural Network for Conversational Emotion Recognition
- Blog: Learning Unitary Operators with Help From u(n)
- Blog: AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks
- Blog: Rotational Unit of Memory
- Blog: Adaptive-saturated RNN: Remember more with less instability
- Blog: Complex Gated Recurrent Neural Networks
- Blog: DOSnet as a Non-Black-Box PDE Solver: When Deep Learning Meets Operator Splitting
- Blog: Parallelization of Non-linear State-Space Models: Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling
- Blog: Unitary Branching Programs: Learnability and Lower Bounds
- Blog: Simplifying and Understanding State Space Models with Diagonal Linear RNNs
- Blog: When recalling in-context, Transformers are not SSMs
- Blog: Fast Graph Convolutional Recurrent Neural Networks
- Blog: Bridging Expressivity and Scalability with Adaptive Unitary SSMs
- Blog: Resurrecting Recurrent Neural Networks for Long Sequences
- Blog: Optoelectronic recurrent neural network using optical-electrical-optical converters with RC delay
- Blog: Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs
- Blog: Path Development Network with Finite-dimensional Lie Group Representation
- Blog: Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections
- Blog: Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothness
- Blog: On the biological plausibility of orthogonal initialisation for solving gradient instability in deep neural networks
- Blog: Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues
- Blog: Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues
- Blog: CWY Parametrization for Scalable Learning of Orthogonal and Stiefel Matrices
- Blog: Complex Unitary Recurrent Neural Networks Using Scaled Cayley Transform
- Blog: Shuffling Recurrent Neural Networks
- Blog: Rotational Unit of Memory
- Blog: Residual Reservoir Computing Neural Networks for Time-series Classification
- Blog: Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group
- Blog: Kronecker Recurrent Units
- Blog: Learning Chaos In A Linear Way
- Blog: Orthogonal RNNs and Long-Memory Tasks
- Blog: Recurrent Orthogonal Networks and Long-Memory Tasks
- Blog: Input-Output Equivalence of Unitary and Contractive RNNs
- Blog: Advancing Regular Language Reasoning in Linear Recurrent Neural Networks
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_unitary_weight_constraint_a7490c2a,
title = {unitary weight constraint},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unitary-weight-constraint/rdr_a7490c2a0c4b4385b8f452dc1ac881e5},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_unitary_weight_constraint_a7490c2a_v1,
title = {unitary weight constraint},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unitary-weight-constraint/rdr_a7490c2a0c4b4385b8f452dc1ac881e5/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}